Nowadays, medical imaging has almost completely replaced traditional techniques for diagnosis and treatment planning due to their non-invasiveness, speed and ease of manipulation. Due to their popularity the medical imaging pushed the bottleneck towards the medical staff that, post-acquisition, have to analyse each case. This process is not only slow but also subjective to a level that it becomes error prone. The anterior cruciate ligament (ACL) is one of the most injured ligaments of the knee. Injuries occur predominantly in a young and sports-active population. Many patients are left with significant disability following injury to the ACL. The injury leads to alteration in the mechanics of the knee. Because some of the cases require surgery it is imperative to be able to classify and detect ACL pathology with high accuracy. Hence this paper studies the usage of pre-trained convolutional neural networks with residual connections (ResNet), in conjunction with image processing techniques to detect ACL pathology and distinguish between multiple tear levels. The ResNet used is not the vanilla ResNet but rather a modified version adapted to work with 3D volumes composed of 2D images (slices). With an obtained accuracy of 87% it is safe to say that the model's output can be successfully used by radiologists to set a 1st baseline diagnostic without any effort almost instantly.

This paper explores new methods for increasing the safety level of the data transfer between electronic control units (ECUs) and actuators in automotive communication. It is proposed to introduce an end-to-end (E2E) module in automotive actuators to check the integrity of the data received through a standard automotive communication bus. The model contains hardware modules that implement the end-to-end communication checking (E2E Check) mechanism, as is defined by the Automotive Open System Architecture (AUTOSAR) standard. By integrating this module into automotive actuators, it is possible to connect them directly to the communication bus inside the vehicle, due to the possibility of verifying the integrity of the data received through the communication bus. The communication bus in this case could be (but not limited to) LIN (Local Interconnection Network), CAN (Controller Area Network) or FlexRay. This paper describes the hardware model, design, and mapping of the E2E communication checking module in a Field Programmable Gate Array (FPGA) device. The proposed hardware model is fully configurable in terms of the structure of the received message from the communication bus, as is requested by the automotive E2E standard. The validation of the E2E communication checking module was done by using the data received from an E2E automotive sensor proposed by authors in previous works. Another validation method, presented in this paper, is to make a comparison of the status returned by the E2E communication checking module with the status provided by the AUTOSAR software E2E library, in context of several configurations of the received messages.

The systems used in the automotive field for V2X (vehicle-to-everyone) communication represent one of the main points in the development of the autonomous vehicles. The design of an ECU (Electronic Control Unit) in order to ensure commu-nications between vehicles is achieved by most car companies. The standard used in the development of this ECU is AUTOSAR (Automotive Open System Architecture). This paper presents how an implemented V2V / V2I system (vehicle-to-vehicle / vehicle-to-infrastructure) is converted to the AUTOSAR architecture. It contains the presentation of the methods of development and implementation of the system on the vehicles, regardless of their age. The proposed V2V / V2I communication system called CommA_v.x (Communication Auto-motive x version) is a system that communicates with the main ECU of the vehicle, distance sensors located on the vehicle, road infrastructure, vehicles around the car but also with the owner / driver. Also, this paper presents the hardware and software differ-ences between the versions of this system, including the simulation of functionality in road traffic.

The purpose of this research article is to create an optimized purpose for the Dijkstra algorithm, with a superior degree of efficiency. This research proposes also, in the first instance, an innovative and efficient analysis of the Dijkstra's and Roy-Floyd algorithms. This proposed method is useful in various application cases, such as information grouping systems associated with a graph with a small but high node density. The analysis part explains the strategies chosen for today's parallel solutions and comparisons with the implemented method. It can be stated that the parallelization solution proposed in the article is specific to a configuration. There will be also presented other strategies considering the grouping systems for the tests with many nodes and edges. The algorithm for determining the shortest path is presented and tested at the multi-language level in different contexts and scenarios.

This paper deals with the design and analysis of new robust-adaptive control schemes for a class of anaerobic wastewater treatment processes. The design procedures are developed under the realistic assumption that the bacterial growth rates are unknown and the influent flow rates are disturbed, but some lower and upper bounds – possibly varying with time – of these uncertainties are known. Firstly, a new state asymptotic observer is designed, and secondly a robust observer for a class of bioprocesses is presented. Using these observers, a new robust-adaptive control scheme is developed and analyzed. This approach is applied to a particular wastewater treatment bioprocess based on anaerobic fermentation and the effectiveness of the designed algorithms is validated by several numerical simulations.